s1 mini IQ3 variants needs about 1.8 GB of memory at IQ3_XS (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB (IQ3_XXS) to 0.4 GB (IQ3_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
s1 mini IQ3 variants is a 752M-parameter Mini model in GGUF format, quantized by PrathamGhaywat. Its trained context length is 40K tokens. The repository has 4 quant files, from 0.3 GB (IQ3_XXS) to 0.4 GB (IQ3_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 0.3 GB | 1.8 GB | Fits | Get file → | |
| IQ3_XS | 0.4 GB | 1.8 GB | Fits | Get file → | |
| IQ3_S | 0.4 GB | 1.8 GB | Fits | Get file → | |
| IQ3_M | 0.4 GB | 1.8 GB | Fits | Get file → |
What GPU do you need for s1 mini IQ3 variants?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is IQ3_M (0.4 GB file, about 1.8 GB in use).
Which s1 mini IQ3 variants quant should you choose?
IQ3_XS (0.4 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ3_XXS at 0.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about s1 mini IQ3 variants
How much VRAM does s1 mini IQ3 variants need?
About 1.8 GB at IQ3_XS with an 8K context window. That is the 0.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run s1 mini IQ3 variants on an 8 GB GPU?
Yes, with IQ3_M: the 0.4 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of s1 mini IQ3 variants GGUF?
It depends on the quant: IQ3_XXS is 0.3 GB, IQ3_XS is 0.4 GB, IQ3_S is 0.4 GB, IQ3_M is 0.4 GB.
What context length does s1 mini IQ3 variants support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download s1 mini IQ3 variants GGUF?
The files are on Hugging Face in the PrathamGhaywat/s1-mini-IQ3-variants-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does s1 mini IQ3 variants use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.